deepseek-ai/DeepSeek-OCR
Compresses visual text into tokens for large language models
View on index · View in 3D Map
Related repos
- DeepSeek-VL2, a vision-language AI modelfor tasks like visual question answeringand OCR
- OCR model using causal flow for document understanding
- Offline OCR using DeepSeek-OCR AI
- unified multimodal model for both understanding and generating images and text
- DeepSeek-V3, a Mixture-of-Experts language model with 671B parameters and 37B active per token, focused on math and coding tasks
- Reproduces DeepSeek-OCR using VILA codebase
- Data analysis platform using large language models
- Rust implementation of DeepSeek-OCR inference stack
- Multimodal large language model that aligns visual and textual embeddings
